Bot is a small application that (for example) executes a simple task much more efficiently and faster than a human being. Internet is full of examples of bots. To save you the time of googling here are few examples: Alexa provided by Amazon helps consumers in shopping, Cortana from Microsoft helps Windows 10 users and Apple’s Siri iOS users.
For service management this means revolution of Service Desks and Call Centers, where the current first level support is replaced by artificial intelligence. There is a clear demand for automation as 80 percent of the questions stated by Service Desk are repetitive that can be easily trained for a bot.
For the past five years chatbots have already been utilized to provide business value. The industry development is accelerating as the giants of IT industry, such as Facebook, Google, Microsoft, Apple and Amazon have had major investments on AI. Also previously internal APIs such as Tensorflow and Facebook Messenger have been published for others to utilize for commercial purposes. In Service Management field ServiceNow acquired machine learning company DxContinuum and Salesforce has gathered more than 100 data scientist to develop AI initiative called Einstein.
Chatbots are usually categorized based on the conversation capability and response mechanism as described in below.
Capability to discuss, means in traditional IT terms data scope that the bot can handle. Open domain means that the bot will try to provide meaningful answer any question instead of a default answer. Closed domain means that bot is built to steer the conversation towards a specifically defined topic and answer questions related to the predefined topic.
Providing the answer is also divided in to two categories: Retrieving the answers (e.g. from database) and creating answers based on the provided text. In both options artificial intelligence can be utilized.
Retrieving answers for open domain is not possible, even for the giants of IT industry as there is no data warehouse that contains correct answer for any questions.
Rulebased chatbots have already achieved commercial success stories such as (i.e. KLM’s chatbot in the Facebook messenger). Rule based chatbots do not create grammatical mistakes, but the disadvange is that they cannot answer new questions that are not identified in the data warehouse.
Chatbots categorized as smart machines analyze the provided data in detail utilizing deep learning methods. In nutshel deep learning means processing the provided data in sequences utilizing algorithms such as logistic or linear regression and teaching the bot with the algorithms after which the bot can intelligently provide an answer to the question. However, this kind of bots have not yet provided commercial success stories in the same manner as rule based bots, due to irrational sentences. If the topic interest you, it is worthwhile reading this research about the topic https://arxiv.org/abs/1409.3215
General AI is a term utilized in the artificial intelligence field to describe the ultimate goal. In short this means a bot that does not have a specific domain for which to provide answer. Instead you could discuss anything with the bot. For example you could first ask about the windows 10 security vulnerabilities and after that ask who the bot thinks will be the next president of France
Research has moved towards the bots creating the answer, but the most successful business cases have utilized rule based bots. We presume that transition from rule based to creating answers will happen through a hybrid model that utilizes practicalities of both areas for example by enriching the answer base by unsupervised learning).
We have created on top of ServiceNow our own AI based chatbot (see screenshot below). If you are interested about the topic, do not hesitate to contact us via the form below.
Screenshort of a chatbot built on top-of ServiceNow
If you want to know more, do not hesitate to contact us!